Abstract: Neural networks encode learned capabilities in their weights, yet extending those capabilities with explicit task knowledge remains a fundamental challenge. Here we show that Weight-Space Programming (WSP), in which executable programs read, construct or modify a network's weights directly, can install new capabilities within trained neural
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
WeightCode: Installing New Capabilities into Neural Networks via Weight-Space Programming
